Merge branch 'fix' into evaluate_current_season

Author: dshemetov

.gitignore

@@ -17,4 +17,4 @@ reports/*.html
 reports/report.md
 cache/
 data/
-.vscode/
+.vscode/

Makefile

@@ -24,34 +24,38 @@ prod: prod-covid prod-flu update_site netlify
 
 submit-covid:
 	cd ../covid19-forecast-hub; \
-	git pull delphi main; \
+	git pull origin main; \
 	git add model-output/CMU-TimeSeries/*; \
+	git add model-output/CMU-climate_baseline/*; \
 	git commit -am "CMU-Delphi submission $(current_date)"; \
 	git push delphi main; \
 	gh pr create --title "CMU-TimeSeries $(current_date)" --repo cdcgov/covid19-forecast-hub
 
 submit-flu:
 	cd ../FluSight-forecast-hub; \
-	git pull delphi main; \
+	git pull origin main; \
 	git add model-output/CMU-TimeSeries/*; \
+	git add model-output/CMU-climate_baseline/*; \
 	git commit -am "CMU-Delphi submission $(current_date)"; \
-	git push delphi; \
+	git push delphi main; \
 	gh pr create --title "CMU-TimeSeries $(current_date)" --repo cdcepi/FluSight-forecast-hub
 
 submit-covid-dry:
 	cd ../covid19-forecast-hub; \
-	git pull delphi main; \
+	git pull origin main; \
 	git add model-output/CMU-TimeSeries/*; \
+	git add model-output/CMU-climate_baseline/*; \
 	git commit -am "CMU-Delphi submission $(current_date)"; \
 	git push delphi main; \
 	gh pr create --title "CMU-TimeSeries $(current_date)" --repo cdcgov/covid19-forecast-hub --dry-run
 
 submit-flu-dry:
 	cd ../FluSight-forecast-hub; \
-	git pull delphi main; \
+	git pull origin main; \
 	git add model-output/CMU-TimeSeries/*; \
+	git add model-output/CMU-climate_baseline/*; \
 	git commit -am "CMU-Delphi submission $(current_date)"; \
-	git push delphi; \
+	git push delphi main; \
 	gh pr create --title "CMU-TimeSeries $(current_date)" --repo cdcepi/FluSight-forecast-hub --dry-run
 
 submit: submit-covid submit-flu

R/aux_data_utils.R

@@ -326,9 +326,8 @@ get_health_data <- function(as_of, disease = c("covid", "flu")) {
 
   most_recent_row <- meta_data %>%
     # update_date is actually a time, so we need to filter for the day after.
-    filter(update_date <= as_of + 1) %>%
-    arrange(desc(update_date)) %>%
-    slice(1)
+    filter(update_date <= as.Date(as_of) + 1) %>%
+    slice_max(update_date)
 
   if (nrow(most_recent_row) == 0) {
     cli::cli_abort("No data available for the given date.")
@@ -344,9 +343,7 @@ get_health_data <- function(as_of, disease = c("covid", "flu")) {
   if (disease == "covid") {
     data %<>% mutate(
       hhs = previous_day_admission_adult_covid_confirmed +
-        previous_day_admission_adult_covid_suspected +
-        previous_day_admission_pediatric_covid_confirmed +
-        previous_day_admission_pediatric_covid_suspected
+        previous_day_admission_pediatric_covid_confirmed
     )
   } else if (disease == "flu") {
     data %<>% mutate(hhs = previous_day_admission_influenza_confirmed)

R/forecasters/epipredict_utilities.R

@@ -130,9 +130,7 @@ run_workflow_and_format <- function(preproc,
   # keeping only the last time_value for any given location/key
   pred %<>%
     group_by(across(all_of(key_colnames(train_data, exclude = "time_value")))) %>%
-    # TODO: slice_max(time_value)?
-    arrange(time_value) %>%
-    filter(row_number() == n()) %>%
+    slice_max(time_value) %>%
     ungroup()
   return(format_storage(pred, as_of))
 }

R/forecasters/forecaster_scaled_pop.R

@@ -142,14 +142,6 @@ scaled_pop <- function(epi_data,
     )
   }
 
-  df <- preproc %>%
-    prep(epi_data) %>%
-    bake(epi_data)
-  write_rds(df, "df2.rds")
-
-  df1 <- read_rds("df1.rds")
-  df2 <- read_rds("df2.rds")
-
   # with all the setup done, we execute and format
   pred <- run_workflow_and_format(preproc, postproc, trainer, season_data, epi_data)
   # now pred has the columns

R/scoring.R

@@ -12,26 +12,6 @@ evaluate_predictions <- function(forecasts, truth_data) {
     must.include = c("geo_value", "target_end_date", "true_value")
   )
 
-  browser()
-  joined_forecasts <- left_join(forecasts, truth_data, by = c("geo_value", "target_end_date"))
-
-  joined_forecasts %>%
-    group_by(model, geo_value, forecast_date, target_end_date) %>%
-    summarize(increasing = all(prediction - shift(prediction, 1, 0) > 0)) %>%
-    ungroup() %>%
-    filter(!increasing)
-
-  joined_forecasts %>%
-    filter(geo_value == "ma", forecast_date == "2023-10-21", target_end_date == "2023-10-21")
-
-  # pred_final %>%
-  #   group_by(geo_value, forecast_date, target_end_date) %>%
-  #   summarize(increasing = all(value - shift(value, 1, 0) > 0)) %>%
-  #   ungroup() %>%
-  #   filter(!increasing)
-
-  # joined_forecasts %>% filter(geo_value == "ma", forecast_date == "2023-10-07", target_end_date == "2023-10-21") %>% print(n=50)
-
   forecast_obj <- left_join(forecasts, truth_data, by = c("geo_value", "target_end_date")) %>%
     scoringutils::as_forecast_quantile(
       quantile_level = "quantile",

covid_geo_exclusions.csv

@@ -8,6 +8,14 @@ forecast_date,forecaster,geo_value,weight
 "2024-10-01", "climate_base", "all", 2
 "2024-10-01", "climate_geo_agged", "all", 0.5
 "2024-10-01", "climate_quantile_extrapolated", "all", 0
+# feb 5
+2025-02-05, all, mp, 0
+2025-02-05, windowed_seasonal, all, 3
+2025-02-05, windowed_seasonal_extra_sources, all, 3
+2025-02-05, linear, all, 0.5
+2025-02-05, linearlog, all, 0
+2025-02-05, climate_base, all, 0
+2025-02-05, climate_geo_agged, all, 0.0
 # dec 4th
 "2024-12-04", "all", "mp", 0
 "2024-12-04", "linear", "all", 3

flu_geo_exclusions.csv

@@ -7,6 +7,14 @@ forecast_date,forecaster,geo_value,weight
 2024-10-01, climate_base, all, 0.5
 2024-10-01, climate_geo_agged, all, 0.25
 2024-10-01, climate_quantile_extrapolated, all, 0
+# feb 5
+2025-02-05, all, mp, 0
+2025-02-05, windowed_seasonal, all, 3
+2025-02-05, windowed_seasonal_extra_sources, all, 3
+2025-02-05, linear, all, 0.5
+2025-02-05, linearlog, all, 0
+2025-02-05, climate_base, all, 0
+2025-02-05, climate_geo_agged, all, 0.0
 # jan 8
 2025-01-08, all, mp, 0
 2025-01-08, windowed_seasonal, all, 3

scripts/covid_hosp_explore.R

@@ -19,8 +19,8 @@ fetch_args <- epidatr::fetch_args_list(return_empty = FALSE, timeout_seconds = 4
 # with prototyping the pipeline.
 dummy_mode <- as.logical(Sys.getenv("DUMMY_MODE", FALSE))
 # For testing, reduce dates
-forecast_generation_dates <- forecast_generation_dates[3]
-forecast_dates <- forecast_dates[3]
+forecast_generation_dates <- forecast_generation_dates[1:10]
+forecast_dates <- forecast_dates[1:10]
 
 
 # ================================ FORECASTER PARAMETERS ====================